Background Falls are a leading cause of injury and reduced mobility, particularly among prosthetic users, older adults, and individuals with neuromuscular impairments. Accurate assessment of fall risk is essential for timely interventions, personalized rehabilitation, and overall safety. However, real-world data collection is often constrained by ethical, logistical, and safety considerations, limiting the availability of sufficiently large and diverse datasets.

Aim To develop a synthetic dataset representing low, medium, and high fall risk scenarios and evaluate the performance of machine learning models trained on this data to provide a reproducible framework for fall risk prediction while mitigating challenges associated with real-world data.

Methods A Python-based toolkit was used to generate synthetic accelerometer (accel_x, accel_y, accel_z) and gyroscope (gyro_x, gyro_y, gyro_z) signals for 1,000 samples across three fall risk categories. Key features, including mean, standard deviation, and variability measures, were extracted from these signals. A Random Forest classifier with 100 decision trees was trained on 80% of the dataset and tested on the remaining 20%. Performance was assessed using accuracy, precision, recall, F1-score, and confusion matrices.

Results The classifier achieved an overall accuracy of 80%, with high precision and recall for low-risk (precision 0.90, recall 0.88) and high-risk (precision 0.75, recall 0.88) categories. Medium-risk predictions were less accurate (precision 0.59, recall 0.54). Feature distributions across fall risk levels demonstrated meaningful separation, supporting the utility of synthetic signals in model training.

Conclusion Synthetic accelerometer and gyroscope data can effectively support fall risk classification, offering a reproducible and ethical alternative for algorithm development in the absence of large-scale real-world datasets.

Clinical Relevance This approach facilitates the rapid development and testing of predictive models for fall prevention, enabling safer, data-driven strategies for vulnerable populations such as older adults and prosthetic users.

The authors have declared no competing interest.

This study did not receive any funding

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.

Yes